whisper-medium-ta / README.md
Sonal0205's picture
End of training
7c7f468 verified
|
raw
history blame
2.03 kB
metadata
language:
  - ta
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Medium ta - tamil
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: ta
          split: None
          args: 'config: ta, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 46.70043811610077

Whisper Medium ta - tamil

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4126
  • Wer: 46.7004

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000

Training results

Training Loss Epoch Step Validation Loss Wer
0.1445 1.6807 1000 0.2832 51.7798
0.0281 3.3613 2000 0.3271 49.2744
0.003 5.0420 3000 0.3818 47.0701
0.0011 6.7227 4000 0.4126 46.7004

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1